2026-04-17T01:03:54Zhttps://recercat.cat/oai/request

oai:recercat.cat:10256/23112024-05-22T09:45:57Zcom_2072_452955com_2072_2054col_2072_452957

Using appearance and context for outdoor scene object classification Bosch Rué, Anna Muñoz Pujol, Xavier Martí Bonmatí, Joan Discriminació visual Imatges -- Processament Imatges -- Segmentació Reconeixement òptic de formes Visió per ordinador Computer vision Image processing Imaging segmentation Optical pattern recognition Visual discrimination We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal 2024-05-22T09:45:57Z 2024-05-22T09:45:57Z 2024-05-22T09:45:57Z 2005 info:eu-repo/semantics/article http://hdl.handle.net/10256/2311 info:eu-repo/semantics/altIdentifier/doi/10.1109/ROBOT.2001.933043 info:eu-repo/semantics/altIdentifier/issn/1050-4729 info:eu-repo/semantics/altIdentifier/isbn/0-7803-6576-3 Tots els drets reservats info:eu-repo/semantics/openAccess IEEE © IEEE International Conference on Robotics and Automation : 2001 : Proceedings 2001 ICRA, 2005, vol. 2 Articles publicats (D-ATC)